Image Quality and Lesion Detectability of Lower-Dose Abdominopelvic CT Obtained Using Deep Learning Image Reconstruction

Objective@#To evaluate the image quality and lesion detectability of lower-dose CT (LDCT) of the abdomen and pelvis obtained using a deep learning image reconstruction (DLIR) algorithm compared with those of standard-dose CT (SDCT) images. @*Materials and Methods@#This retrospective study included 123 patients (mean age ± standard deviation, 63 ± 11 years;male:female, 70:53) who underwent contrast-enhanced abdominopelvic LDCT between May and August 2020 and had prior SDCT obtained using the same CT scanner within a year. LDCT images were reconstructed with hybrid iterative reconstruction (h-IR) and DLIR at medium and high strengths (DLIR-M and DLIR-H), while SDCT images were reconstructed with h-IR. For quantitative image quality analysis, image noise, signal-to-noise ratio, and contrast-to-noise ratio were measured in the liver, muscle, and aorta. Among the three different LDCT reconstruction algorithms, the one showing the smallest difference in quantitative parameters from those of SDCT images was selected for qualitative image quality analysis and lesion detectability evaluation. For qualitative analysis, overall image quality, image noise, image sharpness, image texture, and lesion conspicuity were graded using a 5-point scale by two radiologists. Observer performance in focal liver lesion detection was evaluated by comparing the jackknife free-response receiver operating characteristic figures-of-merit (FOM). @*Results@#LDCT (35.1% dose reduction compared with SDCT) images obtained using DLIR-M showed similar quantitative measures to those of SDCT with h-IR images. All qualitative parameters of LDCT with DLIR-M images but image texture were similar to or significantly better than those of SDCT with h-IR images. The lesion detectability on LDCT with DLIR-M images was not significantly different from that of SDCT with h-IR images (reader-averaged FOM, 0.887 vs. 0.874, respectively; p = 0.581). @*Conclusion@#Overall image quality and detectability of focal liver lesions is preserved in contrast-enhanced abdominopelvic LDCT obtained with DLIR-M relative to those in SDCT with h-IR.

Diagnostic Performance of Deep Learning-Based Lesion Detection Algorithm in CT for Detecting Hepatic Metastasis from Colorectal Cancer

Objective@#To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. @*Materials and Methods@#This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. @*Results@#A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). @*Conclusion@#DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.

Characteristics of Patients Presented With Metastases During or After Completion of Chemoradiation Therapy for Locally Advanced Rectal Cancer: A Case Series

Purpose@#Locally advanced rectal cancer (LARC) is managed by chemoradiotherapy (CRT), followed by surgery. Herein we reported patients with metastases during or after CRT. @*Methods@#Data of patients with LARC who received CRT from 2008 to 2017 were reviewed. Patients with metastases after CRT were included. Those with metastatic tumors at the initial diagnosis were excluded. @*Results@#Fourteen patients (1.3%) of 1,092 who received CRT presented with metastases. Magnetic resonance circumferential resection margin (mrCRM) and mesorectal lymph nodes (LNs) were positive in 12 patients (85.7%). Meanwhile, magnetic resonance extramural vascular invasion (mrEMVI) was positive in 10 patients (71.4%). Magnetic resonance tumor regression grade (mrTRG) 4 and mrTRG5 was detected in 5 and 1 patient respectively. Ten patients (71.4%) underwent combined surgery and 3 (21.4%) received palliative chemotherapy. @*Conclusion@#Patients with metastases after CRT showed a higher rate of positive mrCRM, mrEMVI, mesorectal LNs, and poor tumor response. Further studies with a large number of patients are necessary for better survival outcomes in LARC.

Effectiveness of Hepatocellular Carcinoma Surveillance and an Optimal Surveillance Interval:Nationwide Cohort of Korea

Purpose@#To assess associations between surveillance intervals in a national hepatocellular carcinoma (HCC) surveillance program and receiving curative treatment and mortality using nationwide cohort data for Korea. @*Materials and Methods@#Using the National Health Insurance Service Database of Korea, we retrospectively identified 3201852 patients, the target population of the national HCC surveillance program, between 2008 and 2017. After exclusion, a total of 64674 HCC patients were divided based on surveillance intervals: never screened, ≤6 months (6M), 7–12 months (1Y), 13–24 months (2Y), and 25–36 months (3Y). Associations for surveillance interval with the chance to receive curative therapy and all-cause mortality were analyzed. @*Results@#The 6M group (51.9%) received curative therapy more often than the other groups (1Y, 48.3%; 2Y, 43.8%; 3Y, 41.3%; never screened, 34.5%). Odds ratio for receiving curative therapy among the other surveillance interval groups (1Y, 0.87; 2Y, 0.76; 3Y, 0.77;never screened, 0.57; p<0.001) were significantly lower than that of the 6M group. The hazard ratios (HRs) of all-cause mortality were 1.07, 1.14, and 1.37 for 2Y, 3Y, and never screened groups. The HR for the 1Y group (0.96; p=0.092) was not significantly different, and it was lower (0.91; p<0.001) than that of the 6M group after adjustment for lead-time bias. Curative therapy was associated with survival benefits (HR, 0.26; p<0.001). @*Conclusion@#HCC surveillance, especially at a surveillance interval of 6 months, increases the chance to receive curative therapy.

Diagnostic Performance of Deep Learning-Based Lesion Detection Algorithm in CT for Detecting Hepatic Metastasis from Colorectal Cancer

Objective@#To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. @*Materials and Methods@#This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. @*Results@#A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). @*Conclusion@#DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.

Characteristics of Patients Presented With Metastases During or After Completion of Chemoradiation Therapy for Locally Advanced Rectal Cancer: A Case Series

Purpose@#Locally advanced rectal cancer (LARC) is managed by chemoradiotherapy (CRT), followed by surgery. Herein we reported patients with metastases during or after CRT. @*Methods@#Data of patients with LARC who received CRT from 2008 to 2017 were reviewed. Patients with metastases after CRT were included. Those with metastatic tumors at the initial diagnosis were excluded. @*Results@#Fourteen patients (1.3%) of 1,092 who received CRT presented with metastases. Magnetic resonance circumferential resection margin (mrCRM) and mesorectal lymph nodes (LNs) were positive in 12 patients (85.7%). Meanwhile, magnetic resonance extramural vascular invasion (mrEMVI) was positive in 10 patients (71.4%). Magnetic resonance tumor regression grade (mrTRG) 4 and mrTRG5 was detected in 5 and 1 patient respectively. Ten patients (71.4%) underwent combined surgery and 3 (21.4%) received palliative chemotherapy. @*Conclusion@#Patients with metastases after CRT showed a higher rate of positive mrCRM, mrEMVI, mesorectal LNs, and poor tumor response. Further studies with a large number of patients are necessary for better survival outcomes in LARC.

Effectiveness of Hepatocellular Carcinoma Surveillance and an Optimal Surveillance Interval:Nationwide Cohort of Korea

Purpose@#To assess associations between surveillance intervals in a national hepatocellular carcinoma (HCC) surveillance program and receiving curative treatment and mortality using nationwide cohort data for Korea. @*Materials and Methods@#Using the National Health Insurance Service Database of Korea, we retrospectively identified 3201852 patients, the target population of the national HCC surveillance program, between 2008 and 2017. After exclusion, a total of 64674 HCC patients were divided based on surveillance intervals: never screened, ≤6 months (6M), 7–12 months (1Y), 13–24 months (2Y), and 25–36 months (3Y). Associations for surveillance interval with the chance to receive curative therapy and all-cause mortality were analyzed. @*Results@#The 6M group (51.9%) received curative therapy more often than the other groups (1Y, 48.3%; 2Y, 43.8%; 3Y, 41.3%; never screened, 34.5%). Odds ratio for receiving curative therapy among the other surveillance interval groups (1Y, 0.87; 2Y, 0.76; 3Y, 0.77;never screened, 0.57; p<0.001) were significantly lower than that of the 6M group. The hazard ratios (HRs) of all-cause mortality were 1.07, 1.14, and 1.37 for 2Y, 3Y, and never screened groups. The HR for the 1Y group (0.96; p=0.092) was not significantly different, and it was lower (0.91; p<0.001) than that of the 6M group after adjustment for lead-time bias. Curative therapy was associated with survival benefits (HR, 0.26; p<0.001). @*Conclusion@#HCC surveillance, especially at a surveillance interval of 6 months, increases the chance to receive curative therapy.

Development of a multi-channel NIRS-USG hybrid imaging system for detecting prostate cancer and improving the accuracy of imaging-based diagnosis: a phantom study

PURPOSE: This study aimed to develop a multi-channel near-infrared spectroscopy (NIRS) and ultrasonography (USG) fusion imaging system for imaging prostate cancer and to verify its diagnostic capability by applying the hybrid imaging system to a prostate cancer phantom. METHODS: A multi-channel NIRS system using the near-infrared 785-nm wavelength with 12 channels and four detectors was developed. After arranging the optical fibers around a USG transducer, we performed NIRS imaging and grayscale USG imaging simultaneously. Fusion imaging was obtained by processing incoming signals and the spatial reconstruction of NIRS, which corresponded with grayscale USG acquired at the same time. The NIRS-USG hybrid system was applied to a silicone-based optical phantom of the prostate gland containing prostate cancer to verify its diagnostic capability qualitatively. RESULTS: The NIRS-USG hybrid imaging system for prostate cancer imaging simultaneously provided anatomical and optical information with 2-dimensional registration. The hybrid imaging system showed more NIR attenuation over the prostate cancer model than over the model of normal prostate tissue. Its diagnostic capability to discriminate a focal area mimicking the optical properties of prostate cancer from the surrounding background mimicking the optical properties of normal prostate tissue was verified by applying the hybrid system to a silicone-based optical phantom of prostate cancer. CONCLUSION: This study successfully demonstrated that the NIRS-USG hybrid system may serve as a new imaging method for improving the diagnostic accuracy of prostate cancer, with potential utility for future clinical applications.

Extraosseous Ewing's Sarcoma Presented as a Rectal Subepithelial Tumor: Radiological and Pathological Features

PURPOSE: Extraosseous Ewing's sarcoma (EOE) of the rectum is extremely rare: only three cases have been reported in the literature and none of these reports described their imaging findings in detail. Herein, we describe the tumor imaging and pathological features in detail. MATERIALS AND METHODS: We report a case of rectal EOE in a 72-year-old female who received local excision and was provisionally diagnosed with a rectal submucosal spindle cell tumor. We used immunohistochemistry, histopathology, and fluorescence in situ hybridization to characterize the tumor and provide a definitive diagnosis of EOE. RESULTS: MRI revealed a well-demarcated submucosal tumor with heterogeneous enhancement and hemorrhagic foci in rectum. EOE was diagnosed by positive staining of tumor cells for CD99 and Fli-1 by immunohistochemistry and the presence of the EWSR1 gene translocation by fluorescence in situ hybridization. Although the patient underwent radiation treatment and surgery, the tumor recurred after 4 months as revealed by computed tomography and magnetic resonance imaging. CONCLUSION: Rectal EOE may present as a rectal submucosal tumor. The understanding of imaging and histological characteristics of this tumor are critical for accurate diagnosis and appropriate aggressive treatment.